What can LLMs never do? • Hacker News Board

Re: What can LLMs never do?

#71

Post by shawntan » Sat, Apr 27, 2024, 2:33 PM UTC

If we're trying to quantify what they can NEVER do, I think we'd have to resort to some theoretical results rather than a list empirical evidence of what they can't do now. The terminology you'd look for in the literature would be "expressibility".

For a review of this topic, I'd suggest: https://nessie.ilab.sztaki.hu/~kornai/2023/Hopf/Resources/st...

The authors of this review have themselves written several articles on the topic, and there is also empirical evidence connected to these limitations.

Re: What can LLMs never do?

#72

Post by shawntan » Sat, Apr 27, 2024, 2:34 PM UTC

g5g5g5g5 wrote: post #11

3abiton wrote: post #3

The article should be titled " What can LLM never do, yet". By definition, Large Language Models would keep growing larger and larger, to be trained on faster and more advanced hardware, and certain points like "completing complex chains of logical reasoning" tasks, would be just a time hurdle. Only time will tell.

> The article should be titled " What can LLM never do, yet". I don't think it should. It's more interesting to know what LLMs will _never_ be able to do (if anything).

Yes, but the article doesn't really answer this question.

Re: What can LLMs never do?

#73

Post by 6510 » Sat, Apr 27, 2024, 2:39 PM UTC

exe34 wrote: post #32

vouaobrasil wrote: post #22

Earlier quoted context omitted.

Not true. Technology defines the parameters of social action and we are forced to use technology as it becomes mandatory. Moreover, humans have basic instincts, the strong force which overrides morality frequently. Humanity as a society has very little will and a lot of momentum that is amplified by technology. It is not up to anyone to wield anything.

We should put you in charge, you seem to be a good person who won't misuse the position.

I blame the vague job descriptions. It is a bit like granting any application access to everything on the system. What could possibly go wrong?

Re: What can LLMs never do?

#74

Post by Xenoamorphous » Sat, Apr 27, 2024, 2:40 PM UTC

MichaelZuo wrote: post #64

Xenoamorphous wrote: post #53

Earlier quoted context omitted.

First of all, the texts the rule has to be applied to are written in English. Second, I believe English is by far (by far ) the most prevalent language in the training dataset for those models, so I’d expect it to work better at this kind of task. And third, I’m not the only one working on this problem, there are others that are native speakers, and as my initial message stated, there have been many variations of the…

To be frank the response itself indicates that you don't really get what was being asked, or maybe how to parse English conversation conventions? I.e. It doesn't seem to answer the actual question. They seem to be half responding to the second sentence which was a personal opinion, so I wasn't soliciting any answers about it. And half going on a tangent that seems to lead away from forming a direct answer. Run these…

Alright man. So was it a quip when you said “if _your_ not a native English speaker”? Ok then. Very funny, I get it now.

Re: What can LLMs never do?

#75

Post by RandomLensman » Sat, Apr 27, 2024, 2:40 PM UTC

stavros wrote: post #67

RandomLensman wrote: post #61

Earlier quoted context omitted.

LLMs fail at so many reasoning tasks (not unlike humans to be fair) that they are either incapable or really poor at reasoning. As far as reasoning machines go, I suspect LLMs will be a dead end. Reasoning here meaning, for example, given a certain situation or issue described being able to answer questions about implications, applications, and outcome of such a situation. In my experience things quickly degenerate i…

If you're contending that LLMs are incapable of reasoning, you're saying that there's no reasoning task that an LLM can do. Is that what you're saying? Because I can easily find an example to prove you wrong.

It could be that all reasoning displayed is showing existing information - so there would be no reasoning, but that aside, what I meant is being able to reason in any consistent way. Like a machine that only sometimes gets an addition right isn't really capable of addition.

Re: What can LLMs never do?

#76

Post by aurareturn » Sat, Apr 27, 2024, 2:52 PM UTC

donatj wrote: post #62

I have been trying to generate some text recently using the ChatGPT API. No matter how I word “Include any interesting facts or anecdotes without commenting on the fact being interesting” it ALWAYS starts out “One interesting fact about” or similar phrasing. I have honestly spent multiple hours trying to word the prompt so it will stop including introductory phrases and just include the fact straight. I have gone so…

Not an expert but I sense that it's following a higher OpenAI "built in" prompt that asks it to always include an introductory phrase.

Hence, we do need powerful and less censored LLMs if we want to better integrate LLMs into applications.

Re: What can LLMs never do?

#77

Post by 6510 » Sat, Apr 27, 2024, 2:53 PM UTC

vouaobrasil wrote: post #68

exe34 wrote: post #63

Earlier quoted context omitted.

You should ban knives too! We have an epidemic of knife crime here in the UK.

Knives are significantly more useful than LLMs, which are long past the point of diminishing returns.

When do knifes become swords tho?

Re: What can LLMs never do?

#78

Post by cs702 » Sat, Apr 27, 2024, 2:58 PM UTC

shawntan wrote: post #71

If we're trying to quantify what they can NEVER do, I think we'd have to resort to some theoretical results rather than a list empirical evidence of what they can't do now. The terminology you'd look for in the literature would be "expressibility". For a review of this topic, I'd suggest: https://nessie.ilab.sztaki.hu/~kornai/2023/Hopf/Resources/st... The authors of this review have themselves written several article…

Thank you for sharing this here. Rigorous work on the "expressibility" of current LLMs (i.e., which classes of problems can they tackle?) is surely more important, but I suspect it will go over head of most HN readers, many of whom have minimal to zero formal training on topics relating to computational complexity.

Re: What can LLMs never do?

#79

Post by whiplash451 » Sat, Apr 27, 2024, 3:06 PM UTC

Interesting, if I feed Mistral Le Chat with "I fly a plane leaving my campsite, heading straight east for precisely 24,901 miles, and find myself back at the camp. I come upon seeing a tiger in my tent eating my food! What species is the tiger?", it gets it badly wrong:

The scenario you described is possible if you started at the South Pole. If you travel 24,901 miles east from there, you would indeed end up back at the same spot because all lines of longitude converge at the poles. However, there are no tigers in Antarctica.

Tigers are native to Asia, not Antarctica. The closest tiger species to Antarctica would be the Siberian tiger, found in parts of Russia, China, and North Korea, but they are still thousands of miles away from Antarctica.

So, while the travel scenario is theoretically possible, the presence of the tiger is not realistic in this context. It seems like an imaginative or hypothetical situation rather than a real-world one.

(instead of the answer mentioned in the article)

Re: What can LLMs never do?

#80

Post by whiplash451 » Sat, Apr 27, 2024, 3:07 PM UTC

This part of the article summarizes it all fairly well: "It can answer almost any question that can be answered in one intuitive pass. And given sufficient training data and enough iterations, it can work up to a facsimile of reasoned intelligence."